# US 2022/0413182 A1 · Recommendation engine for a cognitive reservoir system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0413182 A1
- Document ID: US20220413182A1
- Status: Published application
- Kind: A1
- Application number: 17/901,629
- Filed: 2022-09-01
- Published: 2022-12-29
- Earliest claimed: 2017-10-11
- Assignees: Beyond Limits, Inc.
- Applicants: Beyond Limits, Inc.
- Inventors: Zackary H. Nolan; Shahram Farhadi Nia
- Web page: https://patentgrep.com/patent/US20220413182A1

## CPC

- G01V 20/00: Geomodelling in general
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06N 3/043: based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
- G06N 3/0499: Feedforward networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Implementations described and claimed herein provide systems and methods for developing a reservoir. In one implementation, a reservoir model is received. The reservoir model includes a static model and a dynamic model. The static model includes one or more clusters of a three-dimensional volume of the reservoir and an uncertainty quantification generated using a neural network. The dynamic model includes pressure values and fluid saturation values propagated across the three-dimensional volume through a nodal connectivity of neighboring clusters. A set of input features is generated from the static model and the dynamic model. The set of input features is related to a drilling attractiveness of a target region of the reservoir using a set of rules executed by a fuzzy inference engine. A quantification of the drilling attractiveness is generated. A recommendation for drilling in the reservoir is output based on the quantification of the drilling attractiveness.

## Claims

### Claim 1

A method for developing drilling assessments of reservoir nodes, the method comprising:
receiving a reservoir model of a reservoir at a fuzzy inference engine, the reservoir model including a static model and a dynamic model, the static model including one or more clusters of a three-dimensional volume of the reservoir and an uncertainty quantification generated using a neural network, the dynamic model including pressure values and fluid saturation values propagated across the three-dimensional volume through a nodal connectivity of neighboring clusters;
generating a set of input features from the static model and the dynamic model associated with a node of the reservoir via the fuzzy inference engine;
outputting a drilling assessment value of the node of the reservoir based on the set of input features using fuzzy logic, wherein the set of input features are represented within a continuum and evaluated against a set of one or more rules; and
determining a ranking of the node based on the outputted value in relation to respective outputted values of other nodes of the reservoir.

### Claim 2 (depends on 1)

The method of claim 1, further comprising mapping the set of input features into linguistic variables according to membership functions, wherein the membership functions used by the fuzzy inference engine are based on a trapezoidal structure where minimum and maximum values are computed in light of an absolute minimum value and an absolute maximum value for each category examined for the reservoir.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
determining the continuum based on a highest value and a lowest value of the outputted value and the respective outputted values; and
indexing different parts of the continuum to correspond to different levels of drilling attractiveness.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
generating an audit trail for each ranking according to the set of one or more rules encoded in a hierarchy of if/then rules;
caching an input value of one of the input features and an evaluation of a current rule in terms of the membership functions for each step in the hierarchy;
reducing a plurality of evaluation into a single quantified result; and
building a tree associated with the audit trail, wherein the tree is traversable in a backward direction to analyze underlying data and logic.

### Claim 5 (depends on 1)

The method of claim 1, wherein outputting the drilling assessment value includes performing a plurality of stages of fuzzy inference on the set of input features.

### Claim 6 (depends on 1)

The method of claim 1, wherein the set of one or more rules includes one or more of energy rules, fault rules, interfering well rules, connected oil volume rules, and drilling rules.

### Claim 7 (depends on 6)

The method of claim 6, wherein at least one of the energy rules, the fault rules, the interfering well rules, the connected oil volume rules, or the drilling rules is obtained through a plurality of stages of fuzzy inference.

### Claim 8

One or more non-transitory tangible computer-readable storage media storing computer-executable instructions for performing a computer process on a computing system, the computer process comprising:
receiving a reservoir model of a reservoir at a fuzzy inference engine, the reservoir model including a static model and a dynamic model, the static model including one or more clusters of a three-dimensional volume of the reservoir and an uncertainty quantification generated using a neural network, the dynamic model including pressure values and fluid saturation values propagated across the three-dimensional volume through a nodal connectivity of neighboring clusters;
generating a set of input features from the static model and the dynamic model associated with a node of the reservoir via the fuzzy inference engine;
outputting a drilling assessment value of the node of the reservoir based on the set of input features using fuzzy logic, wherein the set of input features are represented within a continuum and evaluated against a set of one or more rules; and
determining a ranking of the node based on the outputted value in relation to respective outputted values of other nodes of the reservoir.

### Claim 9 (depends on 8)

The one or more non-transitory tangible computer-readable storage media of claim 8, the computer process further comprising:
mapping the set of input features into linguistic variables according to membership functions, wherein the membership functions used by the fuzzy inference engine are based on a trapezoidal structure where minimum and maximum values are computed in light of an absolute minimum value and an absolute maximum value for each category examined for the reservoir.

### Claim 10 (depends on 9)

The one or more non-transitory tangible computer-readable storage media of claim 9, the computer process further comprising:
determining the continuum based on a highest value and a lowest value of the outputted value and the respective outputted values; and
indexing different parts of the continuum to correspond to different levels of drilling attractiveness.

### Claim 11 (depends on 10)

The one or more non-transitory tangible computer-readable storage media of claim 10, the computer process further comprising:
generating an audit trail for each ranking according to the set of one or more rules encoded in a hierarchy of if/then rules;
caching an input value of one of the input features and an evaluation of a current rule in terms of the membership functions for each step in the hierarchy;
reducing a plurality of evaluation into a single quantified result; and
building a tree associated with the audit trail, wherein the tree is traversable in a backward direction to analyze underlying data and logic.

### Claim 12 (depends on 8)

The one or more non-transitory tangible computer-readable storage media of claim 8, wherein outputting the drilling assessment value includes performing a plurality of stages of fuzzy inference on the set of input features.

### Claim 13 (depends on 8)

The one or more non-transitory tangible computer-readable storage media of claim 8, wherein the set of one or more rules includes one or more of energy rules, fault rules, interfering well rules, connected oil volume rules, and drilling rules.

### Claim 14 (depends on 13)

The one or more non-transitory tangible computer-readable storage media of claim 13, wherein at least one of the energy rules, the fault rules, the interfering well rules, the connected oil volume rules, or the drilling rules is obtained through a plurality of stages of fuzzy inference.

### Claim 15

A system for developing drilling attractiveness of nodes of a reservoir, the system comprising:
a static modeler generating a static model of a reservoir, the static model including one or more clusters of a three-dimensional volume of the reservoir and an uncertainty quantification generated using a neural network;
a dynamic modeler generating a dynamic model of the reservoir including pressure values and fluid saturation values propagated across the three-dimensional volume through a nodal connectivity of neighboring clusters; and
a fuzzy inference engine in communication with the static modeler and the dynamic modeler, the fuzzy inference engine:
generating a set of input features from the static model and the dynamic model associated with a node of the reservoir via the fuzzy inference engine;
outputting a drilling assessment value of the node of the reservoir based on the set of input features using fuzzy logic, wherein the set of input features are represented within a continuum and evaluated against a set of one or more rules; and
determining a ranking of the node based on the outputted value in relation to respective outputted values of other nodes of the reservoir.

### Claim 16 (depends on 15)

The system of claim 15, wherein the fuzzy inference engine:
maps the set of input features into linguistic variables according to membership functions, wherein the membership functions used by the fuzzy inference engine are based on a trapezoidal structure where minimum and maximum values are computed in light of an absolute minimum value and an absolute maximum value for each category examined for the reservoir.

### Claim 17 (depends on 16)

The system of claim 16, wherein the fuzzy inference engine:
determines the continuum based on a highest value and a lowest value of the outputted value and the respective outputted values; and
indexes different parts of the continuum to correspond to different levels of drilling attractiveness.

### Claim 18 (depends on 17)

The system of claim 17, wherein the fuzzy inference engine:
generates an audit trail for each ranking according to the set of one or more rules encoded in a hierarchy of if/then rules;
caches an input value of one of the input features and an evaluation of a current rule in terms of the membership functions for each step in the hierarchy;
reduces a plurality of evaluation into a single quantified result; and
builds a tree associated with the audit trail, wherein the tree is traversable in a backward direction to analyze underlying data and logic.

### Claim 19 (depends on 15)

The system of claim 15, wherein outputting the drilling assessment value includes performing a plurality of stages of fuzzy inference on the set of input features.

### Claim 20 (depends on 15)

The system of claim 15 wherein the set of one or more rules includes one or more of energy rules, fault rules, interfering well rules, connected oil volume rules, and drilling rules.
